This book brings all the major and frontier topics in the field of document analysis together into a single volume, creating a unique reference source that will be invaluable to a large audience of researchers, lecturers and students working in this field. With chapters written by some of the most distinguished researchers active in this field, this book addresses recent advances in digital document processing research and development.

The growth in the amount of data collected and generated has exploded in recent times with the widespread automation of various day-to-day activities, advances in high-level scienti?c and engineering research and the development of e?cient data collection tools. This has given rise to the need for automa- callyanalyzingthedatainordertoextractknowledgefromit, therebymaking the data potentially more useful. Knowledge discovery and data mining (KDD) is the process of identifying valid, novel, potentially useful and ultimately understandable patterns from massive data repositories. It is a multi-disciplinary topic, drawing from s- eral ?elds including expert systems, machine learning, intelligent databases, knowledge acquisition, case-based reasoning, pattern recognition and stat- tics. Many data mining systems have typically evolved around well-organized database systems (e.g., relational databases) containing relevant information. But, more and more, one ?nds relevant information hidden in unstructured text and in other complex forms. Mining in the domains of the world-wide web, bioinformatics, geoscienti?c data, and spatial and temporal applications comprise some illustrative examples in this regard. Discovery of knowledge, or potentially useful patterns, from such complex data often requires the - plication of advanced techniques that are better able to exploit the nature and representation of the data. Such advanced methods include, among o- ers, graph-based and tree-based approaches to relational learning, sequence mining, link-based classi?cation, Bayesian networks, hidden Markov models, neural networks, kernel-based methods, evolutionary algorithms, rough sets and fuzzy logic, and hybrid systems. Many of these methods are developed in the following chapters

This book contains an edited collection of eighteen contributions on soft and hard computing techniques and their applications to autonomous robotic systems. Each contribution has been exclusively written for this volume by a leading researcher. The volume demonstrates the various ways that the soft computing and hard computing techniques can be used in different integrated manners to better develop autonomous robotic systems that can perform various tasks of vision, perception, cognition, thinking, pattern recognition, decision-making, and reasoning and control, amongst others. Each chapter of the book is self-contained and points out the future direction of research.

"It is a must reading for students and researchers interested in exploring the potentials of the fascinating field that will form the basis for the design of the intelligent machines of the future"
(Madan M. Gupta)

As a graduate student at Ohio State in the mid-1970s, I inherited a unique c- puter vision laboratory from the doctoral research of previous students. They had designed and built an early frame-grabber to deliver digitized color video from a (very large) electronic video camera on a tripod to a mini-computer (sic) with a (huge ) disk drive-about the size of four washing machines. They had also - signed a binary image array processor and programming language, complete with a user's guide, to facilitate designing software for this one-of-a-kindprocessor. The overall system enabled programmable real-time image processing at video rate for many operations. I had the whole lab to myself. I designed software that detected an object in the eldofview, trackeditsmovementsinrealtime, anddisplayedarunningdescription of the events in English. For example: "An object has appeared in the upper right corner...Itismovingdownandtotheleft...Nowtheobjectisgettingcloser...The object moved out of sight to the left"-about like that. The algorithms were simple, relying on a suf cient image intensity difference to separate the object from the background (a plain wall). From computer vision papers I had read, I knew that vision in general imaging conditions is much more sophisticated. But it worked, it was great fun, and I was hooked.

Fuzzy sets were first proposed by Lotfi Zadeh in his seminal paper [366] in 1965, and ever since have been a center of many discussions, fervently admired and condemned. Both proponents and opponents consider the argu ments pointless because none of them would step back from their territory. And stiH, discussions burst out from a single sparkle like a conference pa per or a message on some fuzzy-mail newsgroup. Here is an excerpt from an e-mail messagepostedin1993tofuzzy-mail@vexpert. dbai. twvien. ac. at. by somebody who signed "Dave". , . . . Why then the "logic" in "fuzzy logic"? I don't think anyone has successfully used fuzzy sets for logical inference, nor do I think anyone wiH. In my admittedly neophyte opinion, "fuzzy logic" is a misnomer, an oxymoron. (1 would be delighted to be proven wrong on that. ) . . . I carne to the fuzzy literature with an open mind (and open wal let), high hopes and keen interest. I am very much disiHusioned with "fuzzy" per se, but I did happen across some extremely interesting things along the way. " Dave, thanks for the nice quote! Enthusiastic on the surface, are not many of us suspicious deep down? In some books and journals the word fuzzy is religiously avoided: fuzzy set theory is viewed as a second-hand cheap trick whose aim is nothing else but to devalue good classical theories and open up the way to lazy ignorants and newcomers.

Automatic pattern recognition has uses in science and engineering, social sciences and finance. This book examines data complexity and its role in shaping theory and techniques across many disciplines, probing strengths and deficiencies of current classification techniques, and the algorithms that drive them. The book offers guidance on choosing pattern recognition classification techniques, and helps the reader set expectations for classification performance.

Recently, there has been a dramatic increase in the use of sensors in the non-visible bands. As a result, there is a need for existing computer vision methods and algorithms to be adapted for use with non-visible sensors, or for the development of completely new methods and systems. Computer Vision Beyond the Visible Spectrum is the first book to bring together state-of-the-art work in this area. It presents new & pioneering research across the electromagnetic spectrum in the military, commercial, and medical domains. By providing a detailed examination of each of these areas, it focuses on the development of state-of-the-art algorithms and looks at how they can be used to solve existing & new challenges within computer vision. Essential reading for academics & industrial researchers working in the area of computer vision, image processing, and medical imaging, it will also be useful background reading for advanced undergraduate & postgraduate students.

At the frontier of research, this book offers complete coverage of human ear recognition. It explores all aspects of 3D ear recognition: representation, detection, recognition, indexing and performance prediction. It uses large datasets to quantify and compare the performance of various techniques. Features and topics include: Ear detection and recognition in 2D image; 3D object recognition and 3D biometrics; 3D ear recognition; Performance comparison and prediction.

The evolution of technology has set the stage for the rapid growth of the video Web: broadband Internet access is ubiquitous, and streaming media protocols, systems, and encoding standards are mature. In addition to Web video delivery, users can easily contribute content captured on low cost camera phones and other consumer products. The media and entertainment industry no longer views these developments as a threat to their established business practices, but as an opportunity to provide services for more viewers in a wider range of consumption contexts. The emergence of IPTV and mobile video services offers unprecedented access to an ever growing number of broadcast channels and provides the flexibility to deliver new, more personalized video services. Highly capable portable media players allow us to take this personalized content with us, and to consume it even in places where the network does not reach. Video search engines enable users to take advantage of these emerging video resources for a wide variety of applications including entertainment, education and communications. However, the task of information extr- tion from video for retrieval applications is challenging, providing opp- tunities for innovation. This book aims to first describe the current state of video search engine technology and second to inform those with the req- site technical skills of the opportunities to contribute to the development of this field. Today's Web search engines have greatly improved the accessibility and therefore the value of the Web.

A mathematically rigorous but accessible treatment of digital signal processing that intertwines basic theoretical techniques with hands-on laboratory instruction is provided by this book. The book covers various aspects of the digital signal processing (DSP) "problem." It begins with the analysis of discrete-time signals and explains sampling and the use of the discrete and fast Fourier transforms. The second part of the book - covering digital to analog and analog to digital conversion - provides a practical interlude in the mathematical content before Part III lays out a careful development of the Z-transform and the design and analysis of digital filters.

This book features a collection of articles presented at the 2007 Workshop on Advances in Pattern Recognition, which was organized in conjunction with the 5th International Summer School on Pattern Recognition. It provides readers with the state-of-the-art algorithms in the area of pattern recognition as well as a presentation of the cutting edge applications within the field.

This book introduces a dynamic, on-line fuzzy inference system. In this system membership functions and control rules are not determined until the system is applied and each output of its lookup table is calculated based on current inputs. The book describes the real-world uses of new fuzzy techniques to simplify readers' tuning processes and enhance the performance of their control systems. It further contains application examples.

Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. It enables us to develop optimal vision algorithms systematically when used with optimization principles. This book presents a comprehensive study on the use of MRFs for solving computer vision problems. Various vision models are presented in a unified framework, including image restoration and reconstruction, edge and region segmentation, texture, stereo and motion, object matching and recognition, and pose estimation. This third edition includes the most recent advances and has new and expanded sections on topics such as: Bayesian Network; Discriminative Random Fields; Strong Random Fields; Spatial-Temporal Models; Learning MRF for Classification. This book is an excellent reference for researchers working in computer vision, image processing, statistical pattern recognition and applications of MRFs. It is also suitable as a text for advanced courses in these areas.

Principles of Visual Information Retrieval introduces the basic concepts and techniques in VIR and develops a foundation that can be used for further research and study.
Divided into 2 parts, the first part describes the fundamental principles. A chapter is devoted to each of the main features of VIR, such as colour, texture and shape-based search. There is coverage of search techniques for time-based image sequences or videos, and an overview of how to combine all the basic features described and integrate context into the search process.
The second part looks at advanced topics such as multimedia query, specification, visual learning and semantics, and offers state-of-the-art coverage that is not available in any other book on the market.
This book will be essential reading for researchers in VIR, and for final year undergraduate and postgraduate students on courses such as Multimedia Information Retrieval, Multimedia Databases, Computer Vision and Pattern Recognition.

Noisy data appear very naturally in applications where the authentication is based on physical identifiers. This book provides a self-contained overview of the techniques and applications of security based on noisy data. It provides a comprehensive overview of the theory of extracting cryptographic keys from noisy data, and describes applications in the field of biometrics, secure key storage, and anti-counterfeiting.

Communication Acoustics deals with the fundamentals of those areas of acoustics which are related to modern communication technologies. Due to the advent of digital signal processing and recording in acoustics, these areas have enjoyed an enormous upswing during the last 4 decades. The book chapters represent review articles covering the most relevant areas of the field. They are written with the goal of providing students with comprehensive introductions. Further they offer a supply of numerous references to the relevant literature. Besides its usefulness as a textbook, this will make the book a source of valuable information for those who want to improve or refresh their knowledge in the field of communication acoustics - and to work their way deeper into it. Due to its interdisciplinary character Communication Acoustics is bound to attract readers from many different areas, such as: acoustics, cognitive science, speech science, and communication technology.

Correcting the Great Mistake People often mistake one thing for another. That's human nature. However, one would expect the leaders in a particular ?eld of endeavour to have superior ab- ities to discriminate among the developments within that ?eld. That is why it is so perplexing that the technology elite - supposedly savvy folk such as software developers, marketers and businessmen - have continually mistaken Web-based graphics for something it is not. The ?rst great graphics technology for the Web, VRML, has been mistaken for something else since its inception. Viewed variously as a game system, a format for architectural walkthroughs, a platform for multi-user chat and an augmentation of reality, VRML may qualify as the least understood invention in the history of inf- mation technology. Perhaps it is so because when VRML was originally introduced it was touted as a tool for putting the shopping malls of the world online, at once prosaic and horrifyingly mundane to those of us who were developing it. Perhaps those ?rst two initials,"VR,"created expectations of sprawling, photorealistic f- tasy landscapes for exploration and play across the Web. Or perhaps the magnitude of the invention was simply too great to be understood at the time by the many, ironically even by those spending the money to underwrite its development. Regardless of the reasons, VRML suffered in the mainstream as it was twisted to meet unintended ends and stretched far beyond its limitations.

One of the grand challenges for computational intelligence and biometrics is to understand how people process and recognize faces and to develop automated and reliable face recognition systems. Biometrics has become the major component in the complex decision making process associated with security applications. The many challenges addressed for face detection and authentication include cluttered environments, occlusion and disguise, temporal changes, and last but not least, robust training and open set testing.

Reliable Face Recognition Methods seeks to comprehensively address the face recognition problem while drawing inspiration and gaining new insights from complementary fields of endeavor such as neurosciences, statistics, signal and image processing, computer vision, and machine learning and data mining. The book examines the evolution of research surrounding the field to date, explores new directions, and offers specific guidance on the most promising venues for future R&D.

With its well-focused approach and clarity of presentation, this new text/reference is an excellent resource for computer scientists and engineers, researchers, and professionals who need to learn about face recognition. In addition, the book is ideally suited to students studying biometrics, pattern recognition, and human-computer interaction.

This concise but comprehensive textbook reviews the most popular neural-network methods and their associated techniques. Each chapter provides state-of-the-art descriptions of important major research results of the respective neural-network methods. A range of relevant computational intelligence topics, such as fuzzy logic and evolutionary algorithms - powerful tools for neural-network learning - are introduced. The systematic survey of neural-network models and exhaustive references list will point readers toward topics for future research. The algorithms outlined also make this textbook a valuable reference for scientists and practitioners working in pattern recognition, signal processing, speech and image processing, data analysis and artificial intelligence.

Many computer scientists, engineers, applied mathematicians, and physicists use geometry theory and geometric computing methods in the design of perception-action systems, intelligent autonomous systems, and man-machine interfaces. This handbook brings together the most recent advances in the application of geometric computing for building such systems, with contributions from leading experts in the important fields of neuroscience, neural networks, image processing, pattern recognition, computer vision, uncertainty in geometric computations, conformal computational geometry, computer graphics and visualization, medical imagery, geometry and robotics, and reaching and motion planning. For the first time, the various methods are presented in a comprehensive, unified manner.

This handbook is highly recommended for postgraduate students and researchers working on applications such as automated learning; geometric and fuzzy reasoning; human-like artificial vision; tele-operation; space maneuvering; haptics; rescue robots; man-machine interfaces; tele-immersion; computer- and robotics-aided neurosurgery or orthopedics; the assembly and design of humanoids; and systems for metalevel reasoning.

Face detection, because of its vast array of applications, is one of the most active research areas in computer vision. In this book, we review various approaches to face detection developed in the past decade, with more emphasis on boosting-based learning algorithms. We then present a series of algorithms that are empowered by the statistical view of boosting and the concept of multiple instance learning. We start by describing a boosting learning framework that is capable to handle billions of training examples. It differs from traditional bootstrapping schemes in that no intermediate thresholds need to be set during training, yet the total number of negative examples used for feature selection remains constant and focused (on the poor performing ones). A multiple instance pruning scheme is then adopted to set the intermediate thresholds after boosting learning. This algorithm generates detectors that are both fast and accurate. We then present two multiple instance learning schemes for face detection, multiple instance learning boosting (MILBoost) and winner-take-all multiple category boosting (WTA-McBoost). MILBoost addresses the uncertainty in accurately pinpointing the location of the object being detected, while WTA-McBoost addresses the uncertainty in determining the most appropriate subcategory label for multiview object detection. Both schemes can resolve the ambiguity of the labeling process and reduce outliers during training, which leads to improved detector performances. In many applications, a detector trained with generic data sets may not perform optimally in a new environment. We propose detection adaption, which is a promising solution for this problem. We present an adaptation scheme based on the Taylor expansion of the boosting learning objective function, and we propose to store the second order statistics of the generic training data for future adaptation. We show that with a small amount of labeled data in the new environment, the detector's performance can be greatly improved. We also present two interesting applications where boosting learning was applied successfully. The first application is face verification for filtering and ranking image/video search results on celebrities. We present boosted multi-task learning (MTL), yet another boosting learning algorithm that extends MILBoost with a graphical model. Since the available number of training images for each celebrity may be limited, learning individual classifiers for each person may cause overfitting. MTL jointly learns classifiers for multiple people by sharing a few boosting classifiers in order to avoid overfitting. The second application addresses the need of speaker detection in conference rooms. The goal is to find who is speaking, given a microphone array and a panoramic video of the room. We show that by combining audio and visual features in a boosting framework, we can determine the speaker's position very accurately. Finally, we offer our thoughts on future directions for face detection. Table of Contents: A Brief Survey of the Face Detection Literature / Cascade-based Real-Time Face Detection / Multiple Instance Learning for Face Detection / Detector Adaptation / Other Applications / Conclusions and Future Work

We describe in this book, bio-inspired models and applications of hybrid intel- gent systems using soft computing techniques for image analysis and pattern r- ognition based on biometrics and other information sources. Soft Computing (SC) consists of several intelligent computing paradigms, including fuzzy logic, neural networks, and bio-inspired optimization algorithms, which can be used to produce powerful hybrid intelligent systems. The book is organized in five main parts, which contain a group of papers around a similar subject. The first part consists of papers with the main theme of classification methods and applications, which are basically papers that propose new models for classification to solve general pr- lems and applications. The second part contains papers with the main theme of modular neural networks in pattern recognition, which are basically papers using bio-inspired techniques, like modular neural networks, for achieving pattern r- ognition based on biometric measures. The third part contains papers with the theme of bio-inspired optimization methods and applications to diverse problems. The fourth part contains papers that deal with general theory and algorithms of bio-inspired methods, like neural networks and evolutionary algorithms. The fifth part contains papers on computer vision applications of soft computing methods. In the part of classification methods and applications there are 5 papers that - scribe different contributions on fuzzy logic and bio-inspired models with appli- tion in classification for medical images and other data.

Rapid development of computer hardware has enabled usage of automatic object recognition in an increasing number of applications, ranging from industrial image processing to medical applications, as well as tasks triggered by the widespread use of the internet. Each area of application has its specific requirements, and consequently these cannot all be tackled appropriately by a single, general-purpose algorithm. This easy-to-read text/reference provides a comprehensive introduction to the field of object recognition (OR). The book presents an overview of the diverse applications for OR and highlights important algorithm classes, presenting representative example algorithms for each class. The presentation of each algorithm describes the basic algorithm flow in detail, complete with graphical illustrations. Pseudocode implementations are also included for many of the methods, and definitions are supplied for terms which may be unfamiliar to the novice reader. Supporting a clear and intuitive tutorial style, the usage of mathematics is kept to a minimum. Topics and features: presents example algorithms covering global approaches, transformation-search-based methods, geometrical model driven methods, 3D object recognition schemes, flexible contour fitting algorithms, and descriptor-based methods; explores each method in its entirety, rather than focusing on individual steps in isolation, with a detailed description of the flow of each algorithm, including graphical illustrations; explains the important concepts at length in a simple-to-understand style, with a minimum usage of mathematics; discusses a broad spectrum of applications, including some examples from commercial products; contains appendices discussing topics related to OR and widely used in the algorithms, (but not at the core of the methods described in the chapters). Practitioners of industrial image processing will find this simple introduction and overview to OR a valuable reference, as will graduate students in computer vision courses. Marco Treiber is a software developer at Siemens Electronics Assembly Systems, Munich, Germany, where he is Technical Lead in Image Processing for the Vision System of SiPlace placement machines, used in SMT assembly.

Welcome to the proceedings of the Third International Conference on Contemporary Computing, which was held in Noida (outskirts of New Delhi), India. Computing is an exciting and evolving area. This conference, which was jointly organized by the Jaypee Institute of Information Technology, Noida, India and the University of Fl- ida, Gainesville, USA, focused on topics that are of contemporary interest to computer and computational scientists and engineers. The conference had an exciting technical program of 79 papers submitted by - searchers and practitioners from academia, industry, and government to advance the algorithmic, systems, applications, and educational aspects of contemporary comp- ing. These papers were selected from 350 submissions (with an overall acceptance rate of around 23%). The technical program was put together by a distinguished int- national Program Committee consisting of more than 150 members. The Program Committee was led by the following Track Chairs: Arunava Banerjee, Kanad Kishore Biswas, Summet Dua, Prabhat Mishra, Rajat Moona, Sheung-Hung Poon, and Cho-Li Wang. I would like to thank the Program Committee and the Track Chairs for their tremendous effort. I would like to thank the General Chairs, Prof. Sartaj Sahni and Prof. Sanjay Goel, for giving me the opportunity to lead the technical program. Sanjay Ranka

Roboticsis undergoingamajortransformationinscopeanddimension.From a largelydominantindustrialfocus,roboticsis rapidly expandinginto human environments and vigorouslyengaged in its new challenges. Interacting with, assisting, serving, and exploring with humans, the emerging robots will - creasingly touch people and their lives. Beyond its impact on physical robots, the body of knowledge robotics has produced is revealing a much wider range of applications reaching across - verse research areas and scienti?c disciplines, such as: biomechanics, haptics, neurosciences, virtual simulation, animation, surgery, and sensor networks among others. In return, the challenges of the new emerging areas are pr- ing an abundant source of stimulation and insights for the ?eld of robotics. It is indeed at the intersection of disciplines that the most striking advances happen. TheSpringerTractsinAdvancedRobotics(STAR)isdevotedtobringingto the research community the latest advances in the robotics ?eld on the basis of their signi?cance and quality. Through a wide and timely dissemination of critical research developments in robotics, our objective with this series is to promotemoreexchangesandcollaborationsamongtheresearchersinthec- munity and contributeto further advancements inthis rapidlygrowing?eld. The monographwritten byAlejandro DizanVasquez Goveafocusesonthe practicalproblem of moving in a cluttered environment with pedestrians and vehicles. A frameworkbased on Hidden Markov models is developed to learn typical motion patterns which can be used to predict motion on the basis of sensor data. All the theoretical results have been implemented and validated with experiments, using both real and simulated data.